providers.md Raw History Folder

zut providers

zut ships with built-in providers and a model catalog. You can select models with /model, list them with zut --list-models, and add private models in $ZUT_HOME/models.json.

HTTP proxy

Set one global proxy for zut-managed HTTP and HTTPS traffic with the http_proxy key in $ZUT_HOME/config.json:

{
  "http_proxy": "http://127.0.0.1:7890"
}

zut applies this setting at startup. Existing HTTP_PROXY, HTTPS_PROXY, http_proxy, and https_proxy environment variables take precedence for their corresponding protocol. Standard NO_PROXY and no_proxy bypass lists remain effective. Restart zut after changing the setting.

config.json is not a credential store. If the proxy URL contains a username or password, prefer setting the proxy environment variables in a protected shell or service configuration rather than saving those credentials in config.json.

Use /login in interactive mode. Type in either provider picker to filter the list by provider ID or display name.

api key: stores an API key in $ZUT_HOME/auth.json when the provider uses a normal key.
subscription: stores OAuth credentials for subscription-backed providers.

Use /logout to remove stored credentials.

Some providers need more than a single pasted key. For those providers, /login shows setup instructions instead of opening a localhost browser form. This avoids broken browser flows in SSH, containers, and kubectl exec sessions.

Command-backed API keys

A provider can obtain its API key from a password manager or another local program. Configure this directly in $ZUT_HOME/auth.json:

{
  "openai": {
    "api_key_command": {
      "program": "op",
      "args": ["read", "op://Work/OpenAI/credential"],
      "timeout_ms": 120000
    }
  }
}

Custom provider credentials use the same object under additional_api_key_creds:

{
  "additional_api_key_creds": {
    "my-company": {
      "api_key_command": {
        "program": "secret-tool",
        "args": ["read", "my-company-api-key"]
      }
    }
  }
}

The program is started directly rather than through a shell. The timeout defaults to 120 seconds. It must write one non-empty line to stdout, with no more than 64 KiB of output. Trailing CR/LF characters are removed. Successful results stay only in process memory and are reused until zut exits.

Command-backed credentials count as logged in without being executed. zut materializes one only when selecting that provider; background model discovery skips it. /login with a normal key replaces the command, while /logout clears it. Because auth.json can cause program execution, keep it user-writable only and do not use files from untrusted sources.

Setup-instruction providers:

Amazon Bedrock
Google Vertex AI
Cloudflare Workers AI
Cloudflare AI Gateway
Azure OpenAI Responses

Subscription providers

These providers support subscription login:

Provider	Notes
Anthropic	Claude Pro/Max OAuth credentials.
OpenAI Codex	ChatGPT Plus/Pro Codex subscription route. Separate from the OpenAI API-key provider.
Kimi	Kimi subscription login.
xAI	SuperGrok or X Premium device-code login. The browser URL is prefilled with the device code.
GitHub Copilot	GitHub Copilot token flow.

OAuth tokens are stored in $ZUT_HOME/auth.json and refreshed when refresh is available.

API-key providers

These providers can use environment variables. Simple API-key providers can also be configured through /login. Providers that require extra cloud setup show instructions and should be configured with environment variables.

Provider	Environment variable	Stored key
Anthropic	`ANTHROPIC_API_KEY`	`anthropic`
OpenAI	`OPENAI_API_KEY`	`openai`
OpenAI Responses	`OPENAI_API_KEY`	`openai-responses`
Kimi	`KIMI_API_KEY` or `MOONSHOT_API_KEY`	`kimi`
Google Gemini	`GEMINI_API_KEY` or `GOOGLE_API_KEY`	`google`
DeepSeek	`DEEPSEEK_API_KEY`	`deepseek`
Moonshot AI	`MOONSHOT_API_KEY`	`moonshotai`
Moonshot AI China	`MOONSHOT_API_KEY`	`moonshotai-cn`
Groq	`GROQ_API_KEY`	`groq`
xAI	`XAI_API_KEY`	`xai`
Cerebras	`CEREBRAS_API_KEY`	`cerebras`
Together AI	`TOGETHER_API_KEY`	`together`
Hugging Face	`HF_TOKEN`	`huggingface`
OpenRouter	`OPENROUTER_API_KEY`	`openrouter`
Mistral	`MISTRAL_API_KEY`	`mistral`
ZAI	`ZAI_API_KEY`	`zai`
Xiaomi MiMo	`XIAOMI_API_KEY`	`xiaomi`
Xiaomi Token Plan Amsterdam	`XIAOMI_TOKEN_PLAN_AMS_API_KEY`	`xiaomi-token-plan-ams`
Xiaomi Token Plan China	`XIAOMI_TOKEN_PLAN_CN_API_KEY`	`xiaomi-token-plan-cn`
Xiaomi Token Plan Singapore	`XIAOMI_TOKEN_PLAN_SGP_API_KEY`	`xiaomi-token-plan-sgp`
MiniMax	`MINIMAX_API_KEY`	`minimax`
MiniMax China	`MINIMAX_CN_API_KEY` or `MINIMAX_API_KEY`	`minimax-cn`
Fireworks	`FIREWORKS_API_KEY`	`fireworks`
Vercel AI Gateway	`AI_GATEWAY_API_KEY`	`vercel-ai-gateway`
OpenCode Zen	`OPENCODE_API_KEY`	`opencode`
OpenCode Go	`OPENCODE_API_KEY`	`opencode-go`
GitHub Copilot token	`COPILOT_GITHUB_TOKEN` or `GITHUB_COPILOT_TOKEN`	`github-copilot`
Cloudflare Workers AI	`CLOUDFLARE_API_KEY`	`cloudflare-workers-ai`
Cloudflare AI Gateway	`CLOUDFLARE_API_KEY`	`cloudflare-ai-gateway`
Azure OpenAI Responses	`AZURE_OPENAI_API_KEY`	`azure-openai-responses`

Example:

export OPENROUTER_API_KEY=...
zut --provider openrouter

Fast mode

Use /fast or /settings to enable fast mode for subsequent model calls. The setting is off by default and is stored as fast_mode in $ZUT_HOME/config.json.

Fast mode currently requests OpenAI's Fast service tier for OpenAI Chat, OpenAI Responses, and OpenAI Codex requests. Enabling it while using another provider currently returns an error instead of silently changing that provider's request. Subagent children inherit the setting from their parent unless their profile sets fastMode explicitly.

Session identity and caching

zut supplies every provider request with a root cache identity, a conversation-thread identity, and a per-prompt turn ID. They are opaque local correlations; adapters translate them only when their exact provider, model, and endpoint declaration supports it. Resident children share the root cache identity but retain distinct thread identities. The OpenAI/Codex Responses route uses the root identity as prompt_cache_key; declared Codex routes also receive their documented session and thread routing headers. A generic OpenAI-compatible endpoint never receives these extensions merely because it accepts an OpenAI-shaped request. JSON event mode also reports sanitized cache diagnostics (eligible, mode, transport, and continuation). eligible is a conservative local prompt-length estimate; OpenAI performs the authoritative tokenization and cache decision. These records never include prompts, durable IDs, request bodies, or credentials.

When a provider reports cache detail, zut displays cache-read hit rate as cache reads / cache-reporting prompt input. A shown 0% is a confirmed cache miss; no percentage means the provider or historical session did not report cache detail. Cache writes remain separate from that hit rate. Provider retention and eviction, request routing, and OpenAI's 1,024-token eligibility minimum can still produce a miss even when the stable prefix is unchanged.

OpenAI Responses WebSocket mode

For the exact public endpoint https://api.openai.com/v1/responses, zut uses the Responses API WebSocket mode for the OpenAI Responses route. It keeps one connection per conversation thread, sends one response.create at a time, and continues the most recent completed response with previous_response_id only when the complete response-context configuration and prior input prefix match exactly, including the completed assistant output that precedes a new suffix. Compatible continuations send only new tool or user input. The request uses store:false; its only provider-specific handshake header is Authorization: Bearer ..., never the ChatGPT/Codex account, routing, or session headers.

The capability is deliberately not inherited by --base-url, compatible providers, Azure, or the ChatGPT Codex subscription endpoint. Those clients continue to use their declared HTTP/SSE contracts. A request without a logical session ID, a failed WebSocket setup, an injected nonstandard RoundTripper, or a configured proxy falls back to HTTP/SSE with the same logical session/cache identity. Cancellation closes only the active session socket; a normally completed turn keeps it warm for the next continuation.

Local llama.cpp router

The llama.cpp provider connects to a multi-model router and is separate from the ollama provider. Ollama normally uses http://localhost:11434; entering that URL for llama.cpp management produces a 404 because Ollama does not implement the router endpoints.

Install a current llama.cpp build. On macOS:

brew install llama.cpp
# use `brew upgrade llama.cpp` for an existing installation

Start llama-server without --model, -m, or -hf. Those flags select one model and disable the router behavior zut expects.

mkdir -p ~/llama-models

llama-server \
  --models-dir ~/llama-models \
  --no-models-autoload \
  --jinja \
  --host 127.0.0.1 \
  --port 8080 \
  -ngl 999 \
  -c 32768

This configuration discovers GGUF files below ~/llama-models, leaves model loading under explicit user control, enables chat templates, requests GPU offload, and sets a 32K context. Tune the GPU layers and context size for the available memory.

Check the management API before opening zut:

curl http://127.0.0.1:8080/health
curl http://127.0.0.1:8080/models

/models must return JSON with a data array. A 404 indicates the wrong URL, an older server build, or single-model mode.

To save the connection, run /login, choose api key, and select llama.cpp. Enter http://127.0.0.1:8080, without /v1, followed by an optional bearer key. zut validates the URL and stores both values in $ZUT_HOME/auth.json. Environment variables override the saved connection:

export LLAMA_BASE_URL=http://127.0.0.1:8080
export LLAMA_API_KEY=optional-secret

If a key is configured, start the router with the same --api-key value. A server bound only to 127.0.0.1 normally does not need authentication.

After login, /llama becomes visible. It shows model state, searches Hugging Face for GGUF repositories, offers available quantizations, reports download and load progress, and explicitly loads or unloads models. Press d on a router-downloaded cache model to ask the router to remove it after confirmation. Models discovered through --models-dir or a preset are not removable through the router API and must be deleted from their configured source. Some llama.cpp versions retain shared Hugging Face repository artifacts such as mmproj files after removing the selected GGUF; remove that repository's cache directory manually if those artifacts are no longer needed. HF_TOKEN raises Hugging Face API limits and may be required for repository metadata. For gated files, approve access first and provide the authorized token to the llama-server process because the router performs the download.

Opening /model refreshes the router and displays its loaded models under provider llama.cpp. Unloaded models cannot handle inference and therefore remain exclusive to /llama until loaded. Inference is sent to the router's derived /v1 endpoint.

Ollama downloads are stored in Ollama's internal layout and do not automatically become llama.cpp models. Obtain a GGUF copy through /llama or place GGUF files under ~/llama-models, then restart the router after adding files manually.

Cloud providers

Amazon Bedrock

Bedrock is configured with AWS credentials, not a generic zut API-key entry. Use one of these credential sources:

# AWS profile
export AWS_PROFILE=your-profile

# IAM access keys
export AWS_ACCESS_KEY_ID=AKIA...
export AWS_SECRET_ACCESS_KEY=...
export AWS_SESSION_TOKEN=... # only for temporary credentials

# Bedrock API key bearer token
export AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-...

# Region
export AWS_REGION=us-east-1

ECS task roles, IRSA, and other AWS SDK credential-chain sources are also supported.

Example:

AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-... AWS_REGION=us-east-1 \
  zut --provider amazon-bedrock --model anthropic.claude-sonnet-4-5-20250929-v1:0

Some Bedrock models require regional inference-profile IDs for on-demand throughput, such as us. or eu. prefixed model IDs. zut rewrites known families automatically where possible. Claude Opus 5 uses global.anthropic.claude-opus-5; zut maps the bare foundation-model ID to that global profile and supports its adaptive reasoning levels. Explicit profile IDs and ARNs are left unchanged.

Google Vertex AI

Vertex can use a Google API key when available:

export GOOGLE_CLOUD_API_KEY=...
zut --provider google-vertex

For service-account or application-default credentials, set the standard Google environment variables used by your deployment.

Cloudflare AI Gateway

Cloudflare AI Gateway needs a Cloudflare token plus account and gateway IDs:

export CLOUDFLARE_API_KEY=...
export CLOUDFLARE_ACCOUNT_ID=...
export CLOUDFLARE_GATEWAY_ID=...
zut --provider cloudflare-ai-gateway

Cloudflare Workers AI

Workers AI needs a Cloudflare token and account ID:

export CLOUDFLARE_API_KEY=...
export CLOUDFLARE_ACCOUNT_ID=...
zut --provider cloudflare-workers-ai

Azure OpenAI Responses

export AZURE_OPENAI_API_KEY=...
export AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
export AZURE_OPENAI_API_VERSION=v1 # optional, v1 is the default
zut --provider azure-openai-responses

The provider uses Azure's Responses API. If deployment names differ from zut model IDs, map them without changing the catalog:

export AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-5.6-luna=luna-preview,gpt-5.6-sol=sol-preview'

Auth file

Credentials are stored in $ZUT_HOME/auth.json with user-only permissions when zut creates the file.

Example:

{
  "anthropic": { "api_key": "sk-ant-..." },
  "openai": { "api_key": "sk-..." },
  "google": { "api_key": "..." },
  "additional_api_key_creds": {
    "openrouter": { "api_key": "..." },
    "mistral": { "api_key": "..." }
  }
}

The top-level keys are used for providers with dedicated credential fields. Other API-key providers are stored under additional_api_key_creds. Prefer /login so zut writes the correct schema.

Custom providers and models

Use $ZUT_HOME/models.json for private models, deployment aliases, local servers, or OpenAI-compatible gateways that are not in the built-in catalog. User entries override built-in entries with the same provider and model ID, and adding a models.json no longer hides the built-in catalog: your entries are merged on top of the baked-in and live-discovered models.

A top-level provider key that is not a built-in id defines a custom provider. Give it a provider-level baseUrl and an api wire format (openai for OpenAI-compatible Chat Completions, the default, openai-responses for the OpenAI Responses API, or anthropic for the Anthropic Messages API). A model-level baseUrl overrides the provider-level one for that model, and an unknown api value falls back to openai with a warning.

{
  "providers": {
    "my-company": {
      "baseUrl": "https://llm.mycompany.com/v1",
      "api": "openai",
      "models": [
        { "id": "company-llm-v2", "name": "Company LLM v2" }
      ]
    }
  }
}

Custom providers are first-class: they appear in --list-models, /model, and /login. models.json never stores secrets. Supply the key through /login, --api-key, or a derived environment variable in upper snake case, so my-company reads MY_COMPANY_API_KEY. Because many self-hosted gateways do not expose a model-list endpoint, custom provider keys are accepted and stored without a verification probe; an invalid key surfaces on the first model call.

To retrieve this custom provider's key from a password manager, add a matching entry to $ZUT_HOME/auth.json:

{
  "additional_api_key_creds": {
    "my-company": {
      "api_key_command": {
        "program": "op",
        "args": ["read", "op://Work/OpenAI/credential"],
        "timeout_ms": 120000
      }
    }
  }
}

The provider IDs in models.json and auth.json must match. Then select the custom model directly:

zut --provider my-company --model company-llm-v2

Credential resolution

For each request, zut checks credentials in this order:

Explicit CLI key, such as --api-key.
Provider-specific environment variables (including derived custom-provider variables such as MY_COMPANY_API_KEY).
$ZUT_HOME/auth.json, including custom provider keys saved by /login.

models.json itself never stores credentials; it only describes models and their endpoints.

Bedrock then uses the AWS SDK credential chain for the actual request.

source

1# zut providers
2
3zut ships with built-in providers and a model catalog. You can select models
4with `/model`, list them with `zut --list-models`, and add private models in
5`$ZUT_HOME/models.json`.
6
7## HTTP proxy
8
9Set one global proxy for zut-managed HTTP and HTTPS traffic with the `http_proxy` key in `$ZUT_HOME/config.json`:
10
11```json
12{
13  "http_proxy": "http://127.0.0.1:7890"
14}
15```
16
17zut applies this setting at startup. Existing `HTTP_PROXY`, `HTTPS_PROXY`, `http_proxy`, and `https_proxy` environment variables take precedence for their corresponding protocol. Standard `NO_PROXY` and `no_proxy` bypass lists remain effective. Restart zut after changing the setting.
18
19`config.json` is not a credential store. If the proxy URL contains a username or password, prefer setting the proxy environment variables in a protected shell or service configuration rather than saving those credentials in `config.json`.
20
21## Login methods
22
23Use `/login` in interactive mode. Type in either provider picker to filter the list by provider ID or display name.
24
25- `api key`: stores an API key in `$ZUT_HOME/auth.json` when the provider uses a normal key.
26- `subscription`: stores OAuth credentials for subscription-backed providers.
27
28Use `/logout` to remove stored credentials.
29
30Some providers need more than a single pasted key. For those providers,
31`/login` shows setup instructions instead of opening a localhost browser form.
32This avoids broken browser flows in SSH, containers, and `kubectl exec`
33sessions.
34
35### Command-backed API keys
36
37A provider can obtain its API key from a password manager or another local program. Configure this directly in `$ZUT_HOME/auth.json`:
38
39```json
40{
41  "openai": {
42    "api_key_command": {
43      "program": "op",
44      "args": ["read", "op://Work/OpenAI/credential"],
45      "timeout_ms": 120000
46    }
47  }
48}
49```
50
51Custom provider credentials use the same object under `additional_api_key_creds`:
52
53```json
54{
55  "additional_api_key_creds": {
56    "my-company": {
57      "api_key_command": {
58        "program": "secret-tool",
59        "args": ["read", "my-company-api-key"]
60      }
61    }
62  }
63}
64```
65
66The program is started directly rather than through a shell. The timeout defaults to 120 seconds. It must write one non-empty line to stdout, with no more than 64 KiB of output. Trailing CR/LF characters are removed. Successful results stay only in process memory and are reused until zut exits.
67
68Command-backed credentials count as logged in without being executed. zut materializes one only when selecting that provider; background model discovery skips it. `/login` with a normal key replaces the command, while `/logout` clears it. Because `auth.json` can cause program execution, keep it user-writable only and do not use files from untrusted sources.
69
70Setup-instruction providers:
71
72- Amazon Bedrock
73- Google Vertex AI
74- Cloudflare Workers AI
75- Cloudflare AI Gateway
76- Azure OpenAI Responses
77
78## Subscription providers
79
80These providers support subscription login:
81
82| Provider | Notes |
83| --- | --- |
84| Anthropic | Claude Pro/Max OAuth credentials. |
85| OpenAI Codex | ChatGPT Plus/Pro Codex subscription route. Separate from the OpenAI API-key provider. |
86| Kimi | Kimi subscription login. |
87| xAI | SuperGrok or X Premium device-code login. The browser URL is prefilled with the device code. |
88| GitHub Copilot | GitHub Copilot token flow. |
89
90OAuth tokens are stored in `$ZUT_HOME/auth.json` and refreshed when refresh is
91available.
92
93## API-key providers
94
95These providers can use environment variables. Simple API-key providers can
96also be configured through `/login`. Providers that require extra cloud setup
97show instructions and should be configured with environment variables.
98
99| Provider | Environment variable | Stored key |
100| --- | --- | --- |
101| Anthropic | `ANTHROPIC_API_KEY` | `anthropic` |
102| OpenAI | `OPENAI_API_KEY` | `openai` |
103| OpenAI Responses | `OPENAI_API_KEY` | `openai-responses` |
104| Kimi | `KIMI_API_KEY` or `MOONSHOT_API_KEY` | `kimi` |
105| Google Gemini | `GEMINI_API_KEY` or `GOOGLE_API_KEY` | `google` |
106| DeepSeek | `DEEPSEEK_API_KEY` | `deepseek` |
107| Moonshot AI | `MOONSHOT_API_KEY` | `moonshotai` |
108| Moonshot AI China | `MOONSHOT_API_KEY` | `moonshotai-cn` |
109| Groq | `GROQ_API_KEY` | `groq` |
110| xAI | `XAI_API_KEY` | `xai` |
111| Cerebras | `CEREBRAS_API_KEY` | `cerebras` |
112| Together AI | `TOGETHER_API_KEY` | `together` |
113| Hugging Face | `HF_TOKEN` | `huggingface` |
114| OpenRouter | `OPENROUTER_API_KEY` | `openrouter` |
115| Mistral | `MISTRAL_API_KEY` | `mistral` |
116| ZAI | `ZAI_API_KEY` | `zai` |
117| Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
118| Xiaomi Token Plan Amsterdam | `XIAOMI_TOKEN_PLAN_AMS_API_KEY` | `xiaomi-token-plan-ams` |
119| Xiaomi Token Plan China | `XIAOMI_TOKEN_PLAN_CN_API_KEY` | `xiaomi-token-plan-cn` |
120| Xiaomi Token Plan Singapore | `XIAOMI_TOKEN_PLAN_SGP_API_KEY` | `xiaomi-token-plan-sgp` |
121| MiniMax | `MINIMAX_API_KEY` | `minimax` |
122| MiniMax China | `MINIMAX_CN_API_KEY` or `MINIMAX_API_KEY` | `minimax-cn` |
123| Fireworks | `FIREWORKS_API_KEY` | `fireworks` |
124| Vercel AI Gateway | `AI_GATEWAY_API_KEY` | `vercel-ai-gateway` |
125| OpenCode Zen | `OPENCODE_API_KEY` | `opencode` |
126| OpenCode Go | `OPENCODE_API_KEY` | `opencode-go` |
127| GitHub Copilot token | `COPILOT_GITHUB_TOKEN` or `GITHUB_COPILOT_TOKEN` | `github-copilot` |
128| Cloudflare Workers AI | `CLOUDFLARE_API_KEY` | `cloudflare-workers-ai` |
129| Cloudflare AI Gateway | `CLOUDFLARE_API_KEY` | `cloudflare-ai-gateway` |
130| Azure OpenAI Responses | `AZURE_OPENAI_API_KEY` | `azure-openai-responses` |
131
132Example:
133
134```bash
135export OPENROUTER_API_KEY=...
136zut --provider openrouter
137```
138
139## Fast mode
140
141Use `/fast` or `/settings` to enable **fast mode** for subsequent model calls.
142The setting is off by default and is stored as `fast_mode` in
143`$ZUT_HOME/config.json`.
144
145Fast mode currently requests OpenAI's Fast service tier for OpenAI Chat,
146OpenAI Responses, and OpenAI Codex requests. Enabling it while using another
147provider currently returns an error instead of silently changing that provider's
148request. Subagent children inherit the setting from their parent unless their
149profile sets `fastMode` explicitly.
150
151## Session identity and caching
152
153zut supplies every provider request with a root cache identity, a
154conversation-thread identity, and a per-prompt turn ID. They are opaque local
155correlations; adapters translate them only when their exact provider, model,
156and endpoint declaration supports it. Resident children share the root cache
157identity but retain distinct thread identities. The OpenAI/Codex Responses
158route uses the root identity as `prompt_cache_key`; declared Codex routes also
159receive their documented session and thread routing headers. A generic
160OpenAI-compatible endpoint never receives these extensions merely because it
161accepts an OpenAI-shaped request. JSON event mode also reports sanitized cache
162diagnostics (`eligible`, `mode`, `transport`, and `continuation`). `eligible`
163is a conservative local prompt-length estimate; OpenAI performs the authoritative
164tokenization and cache decision. These records never include prompts, durable
165IDs, request bodies, or credentials.
166
167When a provider reports cache detail, zut displays cache-read hit rate as
168`cache reads / cache-reporting prompt input`. A shown `0%` is a confirmed
169cache miss; no percentage means the provider or historical session did not
170report cache detail. Cache writes remain separate from that hit rate. Provider
171retention and eviction, request routing, and OpenAI's 1,024-token eligibility
172minimum can still produce a miss even when the stable prefix is unchanged.
173
174### OpenAI Responses WebSocket mode
175
176For the exact public endpoint `https://api.openai.com/v1/responses`, zut uses
177the Responses API WebSocket mode for the OpenAI Responses route. It keeps one
178connection per conversation thread, sends one `response.create` at a time,
179and continues the most recent completed response with `previous_response_id`
180only when the complete response-context configuration and prior input prefix
181match exactly, including the completed assistant output that precedes a new
182suffix. Compatible continuations send only new tool or user input.
183The request uses `store:false`; its only provider-specific handshake header is
184`Authorization: Bearer ...`, never the
185ChatGPT/Codex account, routing, or session headers.
186
187The capability is deliberately not inherited by `--base-url`, compatible
188providers, Azure, or the ChatGPT Codex subscription endpoint. Those clients
189continue to use their declared HTTP/SSE contracts. A request without a logical
190session ID, a failed WebSocket setup,
191an injected nonstandard RoundTripper, or a configured proxy falls back to
192HTTP/SSE with the same logical session/cache identity. Cancellation closes
193only the active session socket; a normally completed turn keeps it warm for
194the next continuation.
195
196
197## Local llama.cpp router
198
199The `llama.cpp` provider connects to a multi-model router and is separate from the `ollama` provider. Ollama normally uses `http://localhost:11434`; entering that URL for llama.cpp management produces a 404 because Ollama does not implement the router endpoints.
200
201Install a current llama.cpp build. On macOS:
202
203```bash
204brew install llama.cpp
205# use `brew upgrade llama.cpp` for an existing installation
206```
207
208Start `llama-server` without `--model`, `-m`, or `-hf`. Those flags select one model and disable the router behavior zut expects.
209
210```bash
211mkdir -p ~/llama-models
212
213llama-server \
214  --models-dir ~/llama-models \
215  --no-models-autoload \
216  --jinja \
217  --host 127.0.0.1 \
218  --port 8080 \
219  -ngl 999 \
220  -c 32768
221```
222
223This configuration discovers GGUF files below `~/llama-models`, leaves model loading under explicit user control, enables chat templates, requests GPU offload, and sets a 32K context. Tune the GPU layers and context size for the available memory.
224
225Check the management API before opening zut:
226
227```bash
228curl http://127.0.0.1:8080/health
229curl http://127.0.0.1:8080/models
230```
231
232`/models` must return JSON with a `data` array. A 404 indicates the wrong URL, an older server build, or single-model mode.
233
234To save the connection, run `/login`, choose `api key`, and select `llama.cpp`. Enter `http://127.0.0.1:8080`, without `/v1`, followed by an optional bearer key. zut validates the URL and stores both values in `$ZUT_HOME/auth.json`. Environment variables override the saved connection:
235
236```bash
237export LLAMA_BASE_URL=http://127.0.0.1:8080
238export LLAMA_API_KEY=optional-secret
239```
240
241If a key is configured, start the router with the same `--api-key` value. A server bound only to `127.0.0.1` normally does not need authentication.
242
243After login, `/llama` becomes visible. It shows model state, searches Hugging Face for GGUF repositories, offers available quantizations, reports download and load progress, and explicitly loads or unloads models. Press `d` on a router-downloaded cache model to ask the router to remove it after confirmation. Models discovered through `--models-dir` or a preset are not removable through the router API and must be deleted from their configured source. Some llama.cpp versions retain shared Hugging Face repository artifacts such as `mmproj` files after removing the selected GGUF; remove that repository's cache directory manually if those artifacts are no longer needed. `HF_TOKEN` raises Hugging Face API limits and may be required for repository metadata. For gated files, approve access first and provide the authorized token to the `llama-server` process because the router performs the download.
244
245Opening `/model` refreshes the router and displays its loaded models under provider `llama.cpp`. Unloaded models cannot handle inference and therefore remain exclusive to `/llama` until loaded. Inference is sent to the router's derived `/v1` endpoint.
246
247Ollama downloads are stored in Ollama's internal layout and do not automatically become llama.cpp models. Obtain a GGUF copy through `/llama` or place GGUF files under `~/llama-models`, then restart the router after adding files manually.
248
249## Cloud providers
250
251### Amazon Bedrock
252
253Bedrock is configured with AWS credentials, not a generic zut API-key entry.
254Use one of these credential sources:
255
256```bash
257# AWS profile
258export AWS_PROFILE=your-profile
259
260# IAM access keys
261export AWS_ACCESS_KEY_ID=AKIA...
262export AWS_SECRET_ACCESS_KEY=...
263export AWS_SESSION_TOKEN=... # only for temporary credentials
264
265# Bedrock API key bearer token
266export AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-...
267
268# Region
269export AWS_REGION=us-east-1
270```
271
272ECS task roles, IRSA, and other AWS SDK credential-chain sources are also
273supported.
274
275Example:
276
277```bash
278AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-... AWS_REGION=us-east-1 \
279  zut --provider amazon-bedrock --model anthropic.claude-sonnet-4-5-20250929-v1:0
280```
281
282Some Bedrock models require regional inference-profile IDs for on-demand
283throughput, such as `us.` or `eu.` prefixed model IDs. zut rewrites known
284families automatically where possible. Claude Opus 5 uses
285`global.anthropic.claude-opus-5`; zut maps the bare foundation-model ID to that
286global profile and supports its adaptive reasoning levels. Explicit profile IDs
287and ARNs are left unchanged.
288
289### Google Vertex AI
290
291Vertex can use a Google API key when available:
292
293```bash
294export GOOGLE_CLOUD_API_KEY=...
295zut --provider google-vertex
296```
297
298For service-account or application-default credentials, set the standard
299Google environment variables used by your deployment.
300
301### Cloudflare AI Gateway
302
303Cloudflare AI Gateway needs a Cloudflare token plus account and gateway IDs:
304
305```bash
306export CLOUDFLARE_API_KEY=...
307export CLOUDFLARE_ACCOUNT_ID=...
308export CLOUDFLARE_GATEWAY_ID=...
309zut --provider cloudflare-ai-gateway
310```
311
312### Cloudflare Workers AI
313
314Workers AI needs a Cloudflare token and account ID:
315
316```bash
317export CLOUDFLARE_API_KEY=...
318export CLOUDFLARE_ACCOUNT_ID=...
319zut --provider cloudflare-workers-ai
320```
321
322### Azure OpenAI Responses
323
324```bash
325export AZURE_OPENAI_API_KEY=...
326export AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
327export AZURE_OPENAI_API_VERSION=v1 # optional, v1 is the default
328zut --provider azure-openai-responses
329```
330
331The provider uses Azure's Responses API. If deployment names differ from zut
332model IDs, map them without changing the catalog:
333
334```bash
335export AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-5.6-luna=luna-preview,gpt-5.6-sol=sol-preview'
336```
337
338## Auth file
339
340Credentials are stored in `$ZUT_HOME/auth.json` with user-only permissions
341when zut creates the file.
342
343Example:
344
345```json
346{
347  "anthropic": { "api_key": "sk-ant-..." },
348  "openai": { "api_key": "sk-..." },
349  "google": { "api_key": "..." },
350  "additional_api_key_creds": {
351    "openrouter": { "api_key": "..." },
352    "mistral": { "api_key": "..." }
353  }
354}
355```
356
357The top-level keys are used for providers with dedicated credential fields.
358Other API-key providers are stored under `additional_api_key_creds`. Prefer
359`/login` so zut writes the correct schema.
360
361## Custom providers and models
362
363Use `$ZUT_HOME/models.json` for private models, deployment aliases, local
364servers, or OpenAI-compatible gateways that are not in the built-in catalog.
365User entries override built-in entries with the same provider and model ID, and
366adding a `models.json` no longer hides the built-in catalog: your entries are
367merged on top of the baked-in and live-discovered models.
368
369A top-level provider key that is not a built-in id defines a custom provider.
370Give it a provider-level `baseUrl` and an `api` wire format (`openai` for
371OpenAI-compatible Chat Completions, the default, `openai-responses` for the
372OpenAI Responses API, or `anthropic` for the Anthropic Messages API). A
373model-level `baseUrl` overrides the provider-level one for that model, and an
374unknown `api` value falls back to `openai` with a warning.
375
376```json
377{
378  "providers": {
379    "my-company": {
380      "baseUrl": "https://llm.mycompany.com/v1",
381      "api": "openai",
382      "models": [
383        { "id": "company-llm-v2", "name": "Company LLM v2" }
384      ]
385    }
386  }
387}
388```
389
390Custom providers are first-class: they appear in `--list-models`, `/model`, and
391`/login`. `models.json` never stores secrets. Supply the key through `/login`,
392`--api-key`, or a derived environment variable in upper snake case, so
393`my-company` reads `MY_COMPANY_API_KEY`. Because many self-hosted gateways do
394not expose a model-list endpoint, custom provider keys are accepted and stored
395without a verification probe; an invalid key surfaces on the first model call.
396
397To retrieve this custom provider's key from a password manager, add a matching
398entry to `$ZUT_HOME/auth.json`:
399
400```json
401{
402  "additional_api_key_creds": {
403    "my-company": {
404      "api_key_command": {
405        "program": "op",
406        "args": ["read", "op://Work/OpenAI/credential"],
407        "timeout_ms": 120000
408      }
409    }
410  }
411}
412```
413
414The provider IDs in `models.json` and `auth.json` must match. Then select the
415custom model directly:
416
417```sh
418zut --provider my-company --model company-llm-v2
419```
420
421## Credential resolution
422
423For each request, zut checks credentials in this order:
424
4251. Explicit CLI key, such as `--api-key`.
4262. Provider-specific environment variables (including derived custom-provider
427   variables such as `MY_COMPANY_API_KEY`).
4283. `$ZUT_HOME/auth.json`, including custom provider keys saved by `/login`.
429
430`models.json` itself never stores credentials; it only describes models and
431their endpoints.
432
433Bedrock then uses the AWS SDK credential chain for the actual request.

providers.md RawHistoryFolder

zut providers

HTTP proxy

Login methods

Command-backed API keys

Subscription providers

API-key providers

Fast mode

Session identity and caching

OpenAI Responses WebSocket mode

Local llama.cpp router

Cloud providers

Amazon Bedrock

Google Vertex AI

Cloudflare AI Gateway

Cloudflare Workers AI

Azure OpenAI Responses

Auth file

Custom providers and models

Credential resolution

providers.md Raw History Folder